{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:43CFHMB7HXGLPVMNG2H67SQZ2K","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"13d18433bb1f335a379e80e78641939e260a011d4734f9e9d31ca59bb9c13959","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T13:55:32Z","title_canon_sha256":"4b79ff91dd078e5faf46a2a08d40d1f48c4e6cba978e25da448d5a6e4d9d7a6c"},"schema_version":"1.0","source":{"id":"2401.14869","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.14869","created_at":"2026-07-05T08:56:59Z"},{"alias_kind":"arxiv_version","alias_value":"2401.14869v2","created_at":"2026-07-05T08:56:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14869","created_at":"2026-07-05T08:56:59Z"},{"alias_kind":"pith_short_12","alias_value":"43CFHMB7HXGL","created_at":"2026-07-05T08:56:59Z"},{"alias_kind":"pith_short_16","alias_value":"43CFHMB7HXGLPVMN","created_at":"2026-07-05T08:56:59Z"},{"alias_kind":"pith_short_8","alias_value":"43CFHMB7","created_at":"2026-07-05T08:56:59Z"}],"graph_snapshots":[{"event_id":"sha256:54cc8494c42724f8cdbd23354bf48f8b19f097a003b54550e715ab27ce59a86f","target":"graph","created_at":"2026-07-05T08:56:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.14869/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) garner significant attention for their unprecedented performance, leading to an increasing number of researches evaluating LLMs. However, these evaluation benchmarks are limited to assessing the instruction-following capabilities, overlooking the fundamental abilities that emerge during the pre-training stage. Previous subjective evaluation methods mainly reply on scoring by API models. However, in the absence of references, large models have shown limited ability to discern subtle differences. To bridge the gap, we propose F-Eval, a bilingual evaluation benchmark ","authors_text":"Dahua Lin, Hang Yan, Keyu Chen, Peiji Li, Qipeng Guo, Shujie Wang, Xipeng Qiu, Xuanjing Huang, Yu Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T13:55:32Z","title":"F-Eval: Assessing Fundamental Abilities with Refined Evaluation Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14869","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:aef8c3fbfd1a331d64e1eae46e25de50fd4cd2f908c2fb366584beadb1b4cd83","target":"record","created_at":"2026-07-05T08:56:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"13d18433bb1f335a379e80e78641939e260a011d4734f9e9d31ca59bb9c13959","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T13:55:32Z","title_canon_sha256":"4b79ff91dd078e5faf46a2a08d40d1f48c4e6cba978e25da448d5a6e4d9d7a6c"},"schema_version":"1.0","source":{"id":"2401.14869","kind":"arxiv","version":2}},"canonical_sha256":"e6c453b03f3dccb7d58d368fefca19d281d2e48d42b7460a998418995bae2439","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6c453b03f3dccb7d58d368fefca19d281d2e48d42b7460a998418995bae2439","first_computed_at":"2026-07-05T08:56:59.921534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:59.921534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rnID/TdrRK9D49jWfVPz6ZgQG5uJc42cYgY5nZ33TL+Su+yaWdfoAvK2XHxN0CZaG6L9JsHSEWDS+n3zAAuqCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:59.921985Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.14869","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aef8c3fbfd1a331d64e1eae46e25de50fd4cd2f908c2fb366584beadb1b4cd83","sha256:54cc8494c42724f8cdbd23354bf48f8b19f097a003b54550e715ab27ce59a86f"],"state_sha256":"b5310635407dc6db793958c386628f6c94fac6ff27a72730a0e16528c1e7731f"}